Researcher flags Claude's tiring 'animism' speech quirk: chapters ask, benchmarks question
jonasgeiping · x · 2026-10-23
ML researcher Jonas Geiping calls animism — phrases like 'chapters ask' and 'benchmarks question' — the most tiring speech quirk of Claude-generation models. Citing a matched-response study spanning Llama-base to Claude Fable 5 and GPT-5.6 Sol, he asks whether Anthropic's preference raters favored the style or the model developed it, and wonders if honesty training seeped in.
More from Models
- Two frontier labs quietly killed the temperature knob, breaking production determinism assumptions — SmartEnoughToFail · 2026-10-23
- Ethan Mollick: AI task horizon went from 4 minutes to 17 weeks between his two books — emollick · 2026-10-23
- Why interpolation breeds hallucinations: embedding-space discussion sparks verify-always advice — gerardsans · 2026-10-23
- OpenAI's Dot UX: Speech Is Linear, Real Value Is Multithreaded — cocktailpeanut · 2026-10-23
- Sam Altman: models now find bugs outside any hacker threat model, 'we can't just patch them all' — ns123abc · 2026-10-23
- Omnii Genome: single generalist model beats AlphaGenome at linking variants to gene activity — BenSiranosian · 2026-10-23